© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4900
    Prev
    Next
    INDEX
    Explanations

    Key, Here, 3, N, 2, What, K, Sub

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    d
    0.61
    re
    0.60
    pris
    0.59
    dep
    0.59
    ા
    0.55
    daten
    0.54
    ti
    0.54
    rit
    0.53
    ra
    0.53
    𝐩
    0.51
    POSITIVE LOGITS
    }^\
    0.56
    सूत्र
    0.55
    এবং
    0.54
     axiom
    0.54
     tempted
    0.53
     guardianship
    0.53
     breakaway
    0.53
    비
    0.52
     easement
    0.52
    इसका
    0.52
    Activations Density 0.312%

    No Known Activations