© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35372
    Prev
    Next
    INDEX
    Explanations

    receives or presents information

    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
    ID
    0.16
    Ri
    0.16
    RS
    0.16
    KS
    0.16
    R
    0.16
    EMY
    0.16
    SDK
    0.15
    Serializer
    0.15
    Data
    0.15
    DL
    0.15
    POSITIVE LOGITS
    '
    0.14
    в
    0.14
    이지만
    0.14
    ですが
    0.14
     nhưng
    0.13
    ，
    0.13
    ו
    0.13
    いますが
    0.13
    하지만
    0.13
    것도
    0.13
    Activations Density 0.010%

    No Known Activations