© 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. 49491
    Prev
    Next
    INDEX
    Explanations

    H words and their follow-ups

    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
     inh
    0.38
    elih
    0.38
     need
    0.36
    童
    0.36
    AH
    0.35
     FSH
    0.35
     RH
    0.35
     данные
    0.34
     FH
    0.34
    XH
    0.34
    POSITIVE LOGITS
    ಸ್ಥ
    0.38
     '/':
    0.37
    FBSDKError
    0.36
    -:
    0.35
     nia
    0.35
    heen
    0.35
    Parsed
    0.34
     তৎপর
    0.34
    ミア
    0.34
     reprint
    0.34
    Activations Density 0.019%

    No Known Activations