© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51711
    Prev
    Next
    INDEX
    Explanations

    convicted of murder

    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_30_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
     शकते
    0.43
     perdida
    0.38
    oringa
    0.38
     কর্মকর্তারা
    0.36
     जड़
    0.35
    <0x92>
    0.35
    holiday
    0.35
     выхода
    0.35
    sruhe
    0.35
    artiste
    0.35
    POSITIVE LOGITS
     Diskussion
    0.38
    찰
    0.38
     Walt
    0.37
     Alat
    0.37
    LE
    0.36
     piano
    0.36
     صحی
    0.36
     indent
    0.35
    KF
    0.35
     Mouse
    0.35
    Activations Density 0.001%

    No Known Activations