© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 805
    Prev
    Next
    INDEX
    Explanations

    strings with hexadecimal numbers and/or non-standard characters, perhaps encoding data

    oai_token-act-pair · gemini-2.0-flash

    code and symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    v
    -1.63
    j
    -1.56
    g
    -1.47
    f
    -1.47
    h
    -1.44
    z
    -1.37
    r
    -1.34
    n
    -1.34
    b
    -1.32
    c
    -1.28
    POSITIVE LOGITS
    Datuak
    0.69
    styleType
    0.57
    دانشنامهٔ
    0.56
    fjspx
    0.55
    RetentionPolicy
    0.55
    keyColumn
    0.54
    resizing
    0.52
    存于互联网档案馆
    0.52
    SOUNDBITE
    0.52
    jsonPath
    0.52
    Activations Density 14.000%

    No Known Activations