© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109026
    Prev
    Next
    INDEX
    Explanations

    suffix -ion and -ive

    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_1_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
    a
    1.20
     a
    1.16
    ↵↵
    1.12
    in
    1.02
     "
    1.02
    ה
    1.02
     of
    1.00
    ä
    1.00
     de
    0.98
     adjudication
    0.98
    POSITIVE LOGITS
    ꞎ
    1.48
    на
    1.33
    ст
    1.31
    tım
    1.22
    ра
    1.20
    νο
    1.17
    t
    1.15
    dq
    1.11
    txt
    1.08
    tpl
    1.07
    Activations Density 0.000%

    No Known Activations