© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38797
    Prev
    Next
    INDEX
    Explanations

    trapdoor functions, storms, doors

    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_3_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
    같이
    0.64
    ﺃ
    0.63
    ፩
    0.59
    i
    0.58
    3
    0.57
    the
    0.55
    4
    0.55
    ...
    0.55
    Foldout
    0.54
    nala
    0.53
    POSITIVE LOGITS
    ری
    0.96
    ش
    0.79
    ியை
    0.78
    ен
    0.78
     to
    0.77
    ü
    0.71
    то
    0.68
    )。
    0.68
    ра
    0.67
    ре
    0.66
    Activations Density 0.000%

    No Known Activations