© 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. 7294
    Prev
    Next
    INDEX
    Explanations

    longer

    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
     выполнения
    1.81
     improv
    1.66
    क्सन
    1.64
     copolymers
    1.63
     covariance
    1.58
    Ě
    1.58
    २
    1.56
    󠁧
    1.55
     beginnings
    1.51
    என்ன
    1.49
    POSITIVE LOGITS
    zeitig
    1.85
    ं
    1.75
    ிறது
    1.73
     duração
    1.73
    ي
    1.71
    ι
    1.71
    욱
    1.67
    ലൈ
    1.62
    면
    1.60
     afield
    1.56
    Activations Density 0.002%

    No Known Activations