© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5646
    Prev
    Next
    INDEX
    Explanations

    words related to fashion and food, particularly when presented in a conversational or enthusiastic way.

    oai_token-act-pair · gemini-2.0-flash

    Informal, chatty text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     kasarigan
    -0.76
    LayoutPanel
    -0.67
    nofollow
    -0.58
    ái
    -0.58
    Ndr
    -0.55
     resourceCulture
    -0.55
    Convey
    -0.53
    creativecommons
    -0.52
    uebe
    -0.52
     Carbonate
    -0.51
    POSITIVE LOGITS
    Kanpo
    0.51
     count
    0.50
    Bakgrunnsstoff
    0.49
     disambiguazione
    0.48
    เจ
    0.47
    score
    0.47
     AttributeSet
    0.46
    sidemargin
    0.45
    didSet
    0.45
     Count
    0.45
    Activations Density 2.408%

    No Known Activations