© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2826
    Prev
    Next
    INDEX
    Explanations

    fragments of fantasy stories; it is hard to be more specific with the available data.

    oai_token-act-pair · gemini-2.0-flash

    token patterns likely starting with specific prefixes

    np_token-act-pair-logits · gpt-4o-mini

    old age

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MergeFrom
    -0.76
     Roskov
    -0.68
     Paglinawan
    -0.60
    MetaObject
    -0.59
    LookAnd
    -0.59
    bitField
    -0.58
     كومونز
    -0.56
     viewDidLoad
    -0.53
     للمعارف
    -0.52
    AsUp
    -0.52
    POSITIVE LOGITS
    APORE
    0.54
    HandlerContext
    0.50
    illem
    0.50
    amaño
    0.50
    ousand
    0.48
     record
    0.48
    VIER
    0.47
    gestone
    0.47
     sentence
    0.47
     guy
    0.45
    Activations Density 1.582%

    No Known Activations