© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206340
    Prev
    Next
    INDEX
    Explanations

    localized details or 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_10_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
    )."
    0.23
     childish
    0.22
    ั
    0.21
    ).
    0.21
     pares
    0.21
     Venetian
    0.20
    i
    0.20
    ीकरण
    0.20
     paradig
    0.20
    पणे
    0.19
    POSITIVE LOGITS
    R
    0.32
    on
    0.30
    to
    0.29
    ع
    0.26
    IoT
    0.26
    S
    0.25
    fix
    0.25
    Consume
    0.24
    lock
    0.24
    Sink
    0.24
    Activations Density 0.004%

    No Known Activations