© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7994
    Prev
    Next
    INDEX
    Explanations

    time interval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    л
    1.20
     prong
    1.06
    ि
    1.02
    -\
    0.95
    ಾ
    0.92
     Revis
    0.91
     fórm
    0.91
     meteen
    0.89
    $$
    0.88
    মূলক
    0.86
    POSITIVE LOGITS
    ون
    1.10
    ности
    1.08
    يت
    1.04
    THRESHOLD
    1.04
    ɴ
    1.04
    𝐧
    1.01
    髦
    1.00
    BufferedReader
    1.00
    ção
    0.99
    neider
    0.98
    Activations Density 0.000%

    No Known Activations