© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4409
    Prev
    Next
    INDEX
    Explanations

    words that indicate a progression from one location to another, often vertically

    oai_token-act-pair · gemini-2.0-flash

    Top to bottom sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    TypedDataSet
    -0.61
    }}}
    -0.60
    tison
    -0.60
    MessageTagHelper
    -0.60
    AsUp
    -0.55
     Baillargeon
    -0.54
     CreateTagHelper
    -0.53
     Emin
    -0.52
    nościo
    -0.52
     discogs
    -0.50
    POSITIVE LOGITS
     real
    0.45
    ivably
    0.45
    ANTES
    0.45
     sés
    0.44
    gebir
    0.44
     gradual
    0.44
    ModelAdmin
    0.44
     Exacts
    0.44
    rrggbb
    0.44
    actos
    0.43
    Activations Density 0.939%

    No Known Activations