© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12815
    Prev
    Next
    INDEX
    Explanations

    famous people's names

    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
    缄
    0.53
    োজনের
    0.51
    ohia
    0.48
    utico
    0.48
    ong
    0.47
    JSPA
    0.47
    ),
    0.47
    onta
    0.47
    ຖືກ
    0.46
    </td>
    0.46
    POSITIVE LOGITS
    ън
    0.59
    და
    0.55
    ър
    0.55
     Addresses
    0.52
     地址
    0.52
     Workout
    0.52
    ής
    0.49
    そもそも
    0.49
     অথবা
    0.48
    ене
    0.48
    Activations Density 0.001%

    No Known Activations