© 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. 261241
    Prev
    Next
    INDEX
    Explanations

    veracity, dictum

    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
    a
    1.77
    t
    1.69
    ai
    1.59
    j
    1.55
    an
    1.50
    I
    1.49
    o
    1.46
    ва
    1.41
     an
    1.38
     you
    1.30
    POSITIVE LOGITS
    سي
    1.26
     amoureux
    1.20
    ).}
    1.16
    0
    1.16
    7
    1.13
     сем
    1.12
    يا
    1.10
    كم
    1.09
    5
    1.08
    '
    1.07
    Activations Density 0.000%

    No Known Activations