© 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. 10711
    Prev
    Next
    INDEX
    Explanations

    words ending in "l" or starting with "Dip-", as well as the fragment "vel".

    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
    le
    -0.93
    la
    -0.90
    ling
    -0.89
    led
    -0.88
    las
    -0.86
    lo
    -0.86
    lin
    -0.86
    los
    -0.85
    lan
    -0.84
    les
    -0.83
    POSITIVE LOGITS
    amię
    0.38
    TagMode
    0.37
    principalColumn
    0.36
    neiden
    0.35
     jPanel
    0.34
    ünst
    0.33
    endphp
    0.32
    StoredProcedure
    0.32
    miede
    0.31
    FirstResponder
    0.31
    Activations Density 2.386%

    No Known Activations