© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46124
    Prev
    Next
    INDEX
    Explanations

    append followed by (

    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_13_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
    are
    0.75
    РА
    0.58
    रा
    0.56
    is
    0.55
    t
    0.55
    о
    0.55
    曜日
    0.55
     are
    0.54
    ra
    0.53
    ]
    0.52
    POSITIVE LOGITS
    榫
    0.70
    ምና
    0.61
    чә
    0.60
    ция
    0.59
    μού
    0.59
     Menc
    0.59
     மக்க
    0.57
    ið
    0.57
     élevés
    0.55
     Currents
    0.55
    Activations Density 0.002%

    No Known Activations