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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261391
    Prev
    Next
    INDEX
    Explanations

    anchoring

    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_5_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
    ۹
    1.37
    UM
    1.27
    𝗢
    1.26
    arı
    1.17
    ۸
    1.16
    𝗛
    1.14
    AY
    1.12
    OUSE
    1.10
    ON
    1.08
    ANE
    1.08
    POSITIVE LOGITS
    an
    2.14
    지
    1.80
    л
    1.79
    ان
    1.74
    ↵
    1.66
    r
    1.53
    ש
    1.53
    ן
    1.50
    ?
    1.49
    l
    1.48
    Activations Density 0.000%

    No Known Activations