© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11940
    Prev
    Next
    INDEX
    Explanations

    assistance in various languages.

    oai_token-act-pair · gemini-2.0-flash

    movie titles/foreign text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    piac
    -0.43
     haya
    -0.42
     Scan
    -0.42
     nap
    -0.42
     Find
    -0.41
     décal
    -0.40
    InstanceState
    -0.40
    ec
    -0.40
     Bắc
    -0.39
     scramble
    -0.39
    POSITIVE LOGITS
    TagMode
    0.84
     للمعارف
    0.77
     myſelf
    0.69
    istoitu
    0.69
     समीक्षाओं
    0.69
    #+#
    0.69
    ⓧ
    0.68
    consulté
    0.68
    دانشنامهٔ
    0.68
    AndEndTag
    0.65
    Activations Density 1.129%

    No Known Activations