© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35613
    Prev
    Next
    INDEX
    Explanations

    two-dimensional indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     गाँ
    0.42
     अभिन्न
    0.38
    azaki
    0.36
     infinites
    0.36
     Sexuality
    0.35
     nta
    0.35
     者
    0.35
     Parte
    0.34
     hráč
    0.34
     XXI
    0.34
    POSITIVE LOGITS
    órd
    0.35
    Перед
    0.35
    தல
    0.33
    поряд
    0.33
    जि
    0.32
    ressive
    0.31
    Ft
    0.31
    泺
    0.31
    Indoor
    0.31
    ưở
    0.31
    Activations Density 0.010%

    No Known Activations