© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205959
    Prev
    Next
    INDEX
    Explanations

    raising to power

    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_37_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
    િયાન
    0.41
     stateMutability
    0.38
     sunny
    0.37
    ività
    0.36
    atov
    0.36
     באתר
    0.35
    anski
    0.35
    휋
    0.35
     helium
    0.35
    getti
    0.35
    POSITIVE LOGITS
    Enemy
    0.55
     enemy
    0.50
     detain
    0.50
    ENEMY
    0.44
     déten
    0.44
     detainees
    0.44
     Enemy
    0.43
     शत्रु
    0.43
     preventative
    0.43
     আটক
    0.43
    Activations Density 0.001%

    No Known Activations