© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168117
    Prev
    Next
    INDEX
    Explanations

    male-pattern baldness

    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_34_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
     //!
    0.44
    increased
    0.39
    popupIsOpen
    0.39
    Speech
    0.38
     dispersed
    0.38
     speech
    0.38
    Increased
    0.37
    ...\
    0.36
     Increased
    0.36
     testosterone
    0.36
    POSITIVE LOGITS
    啶
    0.37
     shorter
    0.36
     अभिक्रिया
    0.36
    संह
    0.36
    Leben
    0.36
    时长
    0.35
     حلق
    0.35
    াফিক
    0.35
    環
    0.35
    inj
    0.34
    Activations Density 0.002%

    No Known Activations