© 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
    2. Gemma-3-27B-IT
    3. 7-GEMMASCOPE-2-TRANSCODER-262K
    4. 30537
    Prev
    Next
    INDEX
    Explanations

    error and placeholder

    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_7_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
     to
    0.32
     are
    0.27
    </h2>
    0.25
    <0x0D>
    0.24
     and
    0.24
     was
    0.24
     I
    0.22
     at
    0.22
    </h1>
    0.21
    ist
    0.21
    POSITIVE LOGITS
    asadd
    0.18
     ഇത്തരം
    0.18
    데
    0.18
     région
    0.18
     તેમને
    0.18
    ،
    0.17
    ΙΑ
    0.17
    ㅠㅠ
    0.17
     fruitless
    0.17
    etheless
    0.16
    Activations Density 0.024%

    No Known Activations