© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154730
    Prev
    Next
    INDEX
    Explanations

    en

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    NPC
    0.45
    ⮚
    0.44
    ފައި
    0.44
    Har
    0.44
    Np
    0.43
    ffes
    0.43
    Faction
    0.42
    Dai
    0.41
    зию
    0.41
    Happ
    0.41
    POSITIVE LOGITS
    new
    0.51
     K
    0.47
    res
    0.45
     W
    0.43
     Κ
    0.42
     Files
    0.41
    );
    0.40
     )
    0.40
    team
    0.40
    poll
    0.39
    Activations Density 0.000%

    No Known Activations