© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97704
    Prev
    Next
    INDEX
    Explanations

    headfirst, distancing

    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_14_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
    1
    0.15
     posição
    0.12
     gyroscope
    0.12
     maior
    0.11
     position
    0.11
    Lai
    0.11
    Frame
    0.11
     सिन्हा
    0.11
     *
    0.11
    ারি
    0.11
    POSITIVE LOGITS
    uite
    0.13
    ”…
    0.12
    ills
    0.12
    unnels
    0.11
    ubes
    0.11
    大変
    0.11
    geant
    0.10
    linker
    0.10
    inko
    0.10
     unwillingness
    0.10
    Activations Density 0.003%

    No Known Activations