© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97886
    Prev
    Next
    INDEX
    Explanations

    pronouns and following verbs/adjectives

    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_14_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
    ing
    0.66
    ة
    0.57
    ).
    0.51
     shut
    0.50
    don
    0.47
    (
    0.47
    daten
    0.47
    r
    0.47
    rcl
    0.46
     den
    0.46
    POSITIVE LOGITS
    𝑺
    0.67
    ཿ
    0.60
    Peso
    0.59
    Ż
    0.55
    ளும்
    0.55
    YA
    0.54
     vengono
    0.54
     Berat
    0.54
    顴
    0.54
    ◑
    0.54
    Activations Density 0.009%

    No Known Activations