© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167941
    Prev
    Next
    INDEX
    Explanations

    numbers or punctuation followed by rejection

    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_34_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
    idc
    0.42
    ölf
    0.38
    Letters
    0.37
     aden
    0.36
    𝑚
    0.35
    deviceName
    0.35
    සු
    0.34
     රා
    0.34
     मनाई
    0.34
     pice
    0.34
    POSITIVE LOGITS
     Quit
    0.47
     Exclusion
    0.45
     rejected
    0.44
     পরিত্যাগ
    0.44
    失
    0.44
     rejecting
    0.43
     inaction
    0.43
     Reject
    0.43
     vazio
    0.42
    Reject
    0.42
    Activations Density 0.037%

    No Known Activations