© 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. 36439
    Prev
    Next
    INDEX
    Explanations

    reasons, why, because

    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
     implica
    0.34
    alahkan
    0.34
     pemilihan
    0.33
     괴
    0.33
    ម្បី
    0.33
     Dokl
    0.33
    inskii
    0.33
    칩
    0.32
     fatores
    0.31
    சு
    0.31
    POSITIVE LOGITS
     nation
    0.31
     Por
    0.31
    Handler
    0.30
     Sync
    0.30
    因为
    0.29
     शार्
    0.29
     Patch
    0.29
    Est
    0.29
    Por
    0.29
    ern
    0.28
    Activations Density 0.246%

    No Known Activations