© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62464
    Prev
    Next
    INDEX
    Explanations

    positive personal qualities

    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_59_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
     opinion
    0.38
    ).\
    0.36
    俻
    0.36
    attention
    0.36
    tų
    0.35
    opinion
    0.35
     इज़
    0.34
    ²',
    0.33
     isomeric
    0.33
    )$}
    0.33
    POSITIVE LOGITS
     go
    0.96
     own
    0.70
     pay
    0.67
     Go
    0.62
     Own
    0.61
     propres
    0.60
    Own
    0.59
    Go
    0.57
     eigenes
    0.55
     Pay
    0.53
    Activations Density 0.003%

    No Known Activations