© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15948
    Prev
    Next
    INDEX
    Explanations

    technical or descriptive language that includes numbers, measurements and specific processes.

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    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
    〝
    -0.75
    ：……
    -0.63
    :");
    -0.59
    、《
    -0.55
    enumii
    -0.54
    ：“……”
    -0.54
    Personendaten
    -0.54
    einander
    -0.53
    :";
    -0.53
    },{
    -0.52
    POSITIVE LOGITS
     -
    2.88
     –
    2.20
     −
    1.60
     -}
    1.52
     --
    1.52
    €“
    1.41
     $-$
    1.41
     -\
    1.40
     ‐
    1.40
    －
    1.38
    Activations Density 7.952%

    No Known Activations