© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5814
    Prev
    Next
    INDEX
    Explanations

    classification head

    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
    е
    0.84
    การ
    0.72
    ɴ
    0.71
    gsub
    0.70
    dling
    0.69
    𝐄
    0.68
    на
    0.66
     compr
    0.65
     ehemaligen
    0.65
    時候
    0.64
    POSITIVE LOGITS
    ifiably
    0.84
    enes
    0.80
    }/{
    0.72
    )}.
    0.69
    aris
    0.68
     термин
    0.68
    aj
    0.68
    iv
    0.68
    िव
    0.67
    fiction
    0.67
    Activations Density 0.000%

    No Known Activations