© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13231
    Prev
    Next
    INDEX
    Explanations

    prefixes and/or short words that appear at the starts of words

    oai_token-act-pair · gemini-2.0-flash

    Prefixes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     myſelf
    -1.21
     itſelf
    -1.14
     Houſe
    -1.13
     Efq
    -1.12
     Majefty
    -1.12
     Jefus
    -1.10
     Diſ
    -1.09
     pleaſure
    -1.09
     Reſ
    -1.09
     Theſe
    -1.09
    POSITIVE LOGITS
    de
    0.47
    a
    0.40
    di
    0.39
    -
    0.38
    per
    0.38
    and
    0.37
    he
    0.36
    j
    0.35
    in
    0.35
    to
    0.35
    Activations Density 6.210%

    No Known Activations