© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156962
    Prev
    Next
    INDEX
    Explanations

    Imperative verbs + specific continuations

    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_2_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
     Ağustos
    1.33
    Were
    1.23
    ok
    1.17
     añad
    1.15
     powied
    1.13
    ല
    1.09
     август
    1.09
     Direito
    1.08
     Egipto
    1.06
    Have
    1.05
    POSITIVE LOGITS
    so
    1.20
    p
    1.08
    ures
    1.05
     a
    1.05
    ning
    1.02
    ness
    0.99
    人
    0.96
    ी
    0.96
    ست
    0.94
    line
    0.93
    Activations Density 0.000%

    No Known Activations