© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15491
    Prev
    Next
    INDEX
    Explanations

    the effect(s) of something that is being studied, tested, or changed

    oai_token-act-pair · gemini-2.0-flash

    effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     }}">
    -0.54
     made
    -0.53
     hechos
    -0.49
    ())))
    -0.47
    ())));
    -0.46
     als
    -0.46
     their
    -0.46
     qui
    -0.44
     mediana
    -0.44
     the
    -0.44
    POSITIVE LOGITS
    nipeg
    0.73
    脚注の使い方
    0.73
    rinfo
    0.72
     Administrativna
    0.70
     ſy
    0.69
     defaultstate
    0.69
     Houſe
    0.69
     pleaſure
    0.69
    ARROLLO
    0.66
     eſſ
    0.65
    Activations Density 0.606%

    No Known Activations