© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5863
    Prev
    Next
    INDEX
    Explanations

    . news /

    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_39_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
     berl
    0.37
    ंत्र
    0.37
    Chev
    0.36
     જન્મ
    0.36
    จีน
    0.36
    لوم
    0.36
    Boo
    0.36
    躏
    0.35
    Psal
    0.35
    rint
    0.34
    POSITIVE LOGITS
     существенно
    0.41
    dQ
    0.41
    ᵛ
    0.40
     winning
    0.40
    뀨
    0.40
     Mafia
    0.36
    らく
    0.36
     COR
    0.35
     constitut
    0.35
    dde
    0.35
    Activations Density 0.028%

    No Known Activations