© 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. 15999
    Prev
    Next
    INDEX
    Explanations

    LaTeX code with the word "empty" and numbers in it

    oai_token-act-pair · gemini-2.0-flash

    Code/LaTeX formatting

    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
     protocole
    -0.47
    <bos>
    -0.45
    pendidikan
    -0.42
    übt
    -0.42
     electrónicos
    -0.42
    äger
    -0.41
    éramos
    -0.41
     insecto
    -0.41
    ensement
    -0.40
    sdk
    -0.40
    POSITIVE LOGITS
    \{\\
    0.79
     صوتيه
    0.79
    ^(@)
    0.70
     Efq
    0.69
    ngdoc
    0.68
     Jefus
    0.68
     resourceCulture
    0.67
    istoitu
    0.67
    endpush
    0.66
    }$​
    0.66
    Activations Density 17.377%

    No Known Activations