© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14086
    Prev
    Next
    INDEX
    Explanations

    punctuation or logical operators

    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_15_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
     Analytics
    0.14
    𝔦
    0.13
     Problems
    0.12
    Analytics
    0.12
    來自
    0.12
     antiga
    0.11
     Concerns
    0.11
     analytics
    0.11
    analytics
    0.11
    𝗦
    0.11
    POSITIVE LOGITS
    });
    0.11
    整
    0.10
     ходе
    0.10
     условии
    0.09
    നീ
    0.09
     be
    0.09
    യോഗ
    0.09
    茂
    0.09
    }}\
    0.09
     curse
    0.09
    Activations Density 0.224%

    No Known Activations