© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143323
    Prev
    Next
    INDEX
    Explanations

    punctuation and certain words

    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_0_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
    ב
    1.88
    ру
    1.72
    ପ
    1.55
    ພວກເຮົາ
    1.51
    ку
    1.50
    يل
    1.45
    क
    1.45
    и
    1.45
    ک
    1.45
    국
    1.45
    POSITIVE LOGITS
    n
    1.65
    a
    1.34
    r
    1.24
    he
    1.23
    though
    1.13
     thiol
    1.10
     landlord
    1.08
    mental
    1.08
    9
    1.08
    6
    1.08
    Activations Density 0.000%

    No Known Activations