© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40146
    Prev
    Next
    INDEX
    Explanations

    easily, confused, discouraged, scared

    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_11_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
     হবে
    0.63
     idade
    0.63
    morning
    0.62
     കഴിയ
    0.62
    hours
    0.61
    scode
    0.59
     නමුත්
    0.58
    ℡
    0.58
     ලැබ
    0.57
    going
    0.56
    POSITIVE LOGITS
    :
    0.65
    анта
    0.61
    etti
    0.57
    льна
    0.57
    ส
    0.55
     quebr
    0.54
     –
    0.54
     -
    0.53
    ات
    0.53
     assets
    0.52
    Activations Density 0.037%

    No Known Activations