© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90142
    Prev
    Next
    INDEX
    Explanations

    he, her, his

    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
     confond
    0.40
    luğ
    0.39
     Such
    0.39
    निटी
    0.37
     avanti
    0.35
    <0xDE>
    0.35
     Too
    0.35
     Consume
    0.33
    ૄ
    0.33
    ᴼ
    0.33
    POSITIVE LOGITS
     her
    1.12
    here
    1.00
    his
    0.96
     here
    0.95
     he
    0.93
    her
    0.93
    Her
    0.91
     his
    0.91
     Her
    0.88
     الح
    0.86
    Activations Density 0.027%

    No Known Activations