© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6222
    Prev
    Next
    INDEX
    Explanations

    potential

    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
    ين
    3.01
    ení
    2.91
    此之外
    2.63
    ि
    2.55
    в
    2.52
    𝙞
    2.50
     cil
    2.44
    muestra
    2.40
    jenigen
    2.34
    𝙪
    2.31
    POSITIVE LOGITS
     रोजी
    2.58
    いる
    2.32
     phoned
    2.22
    栱
    2.19
     rapides
    2.17
    यूपी
    2.11
    值的
    2.09
    켄
    2.08
    $('#
    2.08
    erade
    2.07
    Activations Density 0.001%

    No Known Activations