© 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. 2871
    Prev
    Next
    INDEX
    Explanations

    uppercase words and acronyms, especially those related to legal, medical, or political issues

    oai_token-act-pair · 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
    !")
    -0.81
    Cordialement
    -0.80
    ]")]
    -0.78
    __':
    -0.74
    ?')
    -0.71
    .³
    -0.71
    ?」
    -0.70
     magasiner
    -0.70
     */;
    -0.69
    »։
    -0.69
    POSITIVE LOGITS
    IVOS
    0.40
    AP
    0.39
    RIED
    0.37
    AC
    0.35
    ERI
    0.35
    IDI
    0.35
    IC
    0.35
    GO
    0.35
    VE
    0.35
    AMO
    0.33
    Activations Density 3.179%

    No Known Activations