© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14032
    Prev
    Next
    INDEX
    Explanations

    online and stack trace

    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_13_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
     progressions
    0.50
     authoritative
    0.48
     conversions
    0.48
    ];
    0.47
    ].
    0.47
    \]
    0.47
     expensive
    0.47
    spy
    0.47
     pregnancies
    0.47
    difficult
    0.46
    POSITIVE LOGITS
    క్కడ
    0.46
     piu
    0.46
    cedor
    0.45
    χαν
    0.44
     almu
    0.44
    嬷
    0.44
     veer
    0.44
     PICTURE
    0.44
    τ
    0.44
    \%$
    0.43
    Activations Density 0.000%

    No Known Activations