© 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. 30939
    Prev
    Next
    INDEX
    Explanations

    will be back or returning

    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
    孵
    0.30
    باد
    0.29
    First
    0.29
    ệm
    0.28
     personalities
    0.28
     prolog
    0.28
    మ
    0.28
     column
    0.28
     incubated
    0.28
     contract
    0.27
    POSITIVE LOGITS
    RetValue
    0.31
     আরও
    0.31
     আরো
    0.31
    Ꮷ
    0.30
     tł
    0.29
    ruptcy
    0.28
     হের
    0.28
    ligare
    0.28
     weiteren
    0.28
    আরো
    0.28
    Activations Density 0.001%

    No Known Activations