© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104137
    Prev
    Next
    INDEX
    Explanations

    generation concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     !==
    0.41
    ํา
    0.38
     Ги
    0.37
    тельности
    0.37
     минима
    0.37
     Gy
    0.37
    合法
    0.36
    тивной
    0.36
     heading
    0.35
     Styl
    0.35
    POSITIVE LOGITS
    ंचे
    0.42
    Ề
    0.40
    шымта
    0.40
    <bbox>
    0.37
     মজুম
    0.37
    }}^{(
    0.37
     épu
    0.36
     Eros
    0.36
    ತ್ವ
    0.36
    Kaynakça
    0.36
    Activations Density 0.001%

    No Known Activations