© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201300
    Prev
    Next
    INDEX
    Explanations

    Allowing yourself or others

    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_12_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
     weir
    0.56
     r
    0.55
    Um
    0.55
    That
    0.51
    Ibid
    0.51
     That
    0.50
    Groups
    0.50
     چھوٹ
    0.49
     р
    0.49
    Gb
    0.49
    POSITIVE LOGITS
     Kavan
    0.52
    მასრულ
    0.52
    ští
    0.51
    рения
    0.50
    ющихся
    0.50
    fatal
    0.49
    countery
    0.48
     武田
    0.48
    getattr
    0.48
    久し
    0.48
    Activations Density 0.005%

    No Known Activations