© 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. 6748
    Prev
    Next
    INDEX
    Explanations

    blues and greens

    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
    den
    2.52
    ení
    2.43
    ारा
    2.34
    рати
    2.33
    ం
    2.18
    дцать
    2.14
     varic
    2.13
    alış
    2.13
     преобразова
    2.08
    ейчас
    2.06
    POSITIVE LOGITS
    ுக
    2.51
    fashioned
    2.41
    檚
    2.32
    ுகளில்
    2.29
    其
    2.24
    িয়ে
    2.23
    нием
    2.22
    zeichen
    2.16
    ли
    2.12
    armed
    2.09
    Activations Density 0.001%

    No Known Activations