© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50163
    Prev
    Next
    INDEX
    Explanations

    apology

    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_30_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
     unsatisfactory
    0.36
     disappointing
    0.32
     médiocrement
    0.32
    겉
    0.32
     disappointed
    0.31
     Apparently
    0.31
     ព
    0.30
     poorly
    0.30
     unsatisf
    0.30
     merhaba
    0.29
    POSITIVE LOGITS
     kich
    0.30
     focus
    0.29
     tune
    0.29
    哉
    0.29
    Emp
    0.28
     trespass
    0.28
    賃
    0.28
    Timeout
    0.28
    HOUT
    0.28
    olib
    0.28
    Activations Density 0.003%

    No Known Activations