© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86939
    Prev
    Next
    INDEX
    Explanations

    average or typical

    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_18_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
    Ο
    0.18
    錬
    0.18
    α
    0.18
     sealed
    0.17
    ING
    0.16
     unit
    0.16
     проведен
    0.16
    bonding
    0.16
     */;
    0.15
    Ef
    0.15
    POSITIVE LOGITS
     endere
    0.17
    qués
    0.16
     علاقه
    0.16
     தொடர்ப
    0.16
     hùng
    0.15
    𝚃
    0.15
    ்ய
    0.15
    ]^{\
    0.15
     lì
    0.15
    tees
    0.15
    Activations Density 0.003%

    No Known Activations