© 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. 10701
    Prev
    Next
    INDEX
    Explanations

    abbreviations of people's names or names containing "Mel" or "Hel"

    oai_token-act-pair · gemini-2.0-flash

    Names

    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
    stdafx
    -0.55
    NameValuePair
    -0.54
    ivät
    -0.52
    <?
    -0.48
    iela
    -0.47
    Anlage
    -0.47
    platforms
    -0.46
    adult
    -0.46
    iyle
    -0.46
     plages
    -0.46
    POSITIVE LOGITS
    LookAnd
    0.72
    Rüyada
    0.70
     ModelExpression
    0.70
    principalTable
    0.65
     <=",
    0.60
     Infórmanos
    0.60
    UnusedPrivate
    0.60
     consultato
    0.56
    忑
    0.56
    yszcz
    0.54
    Activations Density 1.199%

    No Known Activations