© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232819
    Prev
    Next
    INDEX
    Explanations

    destruction or collapse

    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_32_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
     geom
    0.41
    ্লেখ
    0.38
    oyloxy
    0.37
    观
    0.36
     PublicKey
    0.36
    签名
    0.35
     defList
    0.35
    挪
    0.35
     Key
    0.35
     списка
    0.35
    POSITIVE LOGITS
    確定
    0.39
    circ
    0.37
    担
    0.37
     vence
    0.37
     overshoot
    0.37
    ก็จะ
    0.37
    Wins
    0.36
     circulate
    0.35
    entre
    0.34
     biện
    0.34
    Activations Density 0.001%

    No Known Activations