© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237036
    Prev
    Next
    INDEX
    Explanations

    c# code examples

    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_25_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
     Beds
    0.45
     उच्चारण
    0.41
     Breathing
    0.39
     Stability
    0.39
    撰
    0.39
     createArticle
    0.39
     Building
    0.38
     Pivot
    0.38
     стаби
    0.38
     मिलाने
    0.38
    POSITIVE LOGITS
    whom
    0.42
     whom
    0.41
    ny
    0.39
    Sigma
    0.39
    ी
    0.38
    }{\
    0.37
    ujian
    0.37
    $$\
    0.36
    Politics
    0.36
    Correspondence
    0.36
    Activations Density 0.000%

    No Known Activations