© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126273
    Prev
    Next
    INDEX
    Explanations

    FQDN / FCN / FBN / FRBN

    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_3_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
    ow
    0.68
    دارة
    0.64
     on
    0.61
     punten
    0.61
    佽
    0.61
     bescherm
    0.60
    ial
    0.58
     nej
    0.58
     மதி
    0.58
    and
    0.58
    POSITIVE LOGITS
    ี
    0.55
    isasi
    0.52
    ることが
    0.51
    र्गन
    0.51
    मक
    0.50
    യി
    0.50
    uksi
    0.49
    ুম
    0.48
    t
    0.48
    ッピング
    0.48
    Activations Density 0.000%

    No Known Activations