© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51157
    Prev
    Next
    INDEX
    Explanations

    NIH, unknown

    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_30_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
    </b>
    0.39
     findings
    0.37
     カー
    0.37
     phoned
    0.36
     refus
    0.36
     follow
    0.36
     driving
    0.35
    သွား
    0.35
    ઘ
    0.35
     chauffeur
    0.35
    POSITIVE LOGITS
    unknown
    0.43
    UNKNOWN
    0.42
    clearInterval
    0.40
    概率
    0.40
    uncertain
    0.39
    Computed
    0.39
     undocumented
    0.37
    Unknown
    0.37
    estimation
    0.37
     Estimation
    0.37
    Activations Density 0.000%

    No Known Activations