© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21135
    Prev
    Next
    INDEX
    Explanations

    factual information

    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_56_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
     ‎
    0.37
     ​​​​
    0.35
    ‎
    0.35
    ");*/
    0.34
     ‏
    0.34
     ⠀
    0.34
     ‌
    0.33
     fraternal
    0.33
    ले
    0.32
    }*/
    0.32
    POSITIVE LOGITS
    </strong>
    0.48
    </b>
    0.41
    楨
    0.33
    udon
    0.33
    .(*
    0.33
    تاجها
    0.33
     мину
    0.32
    няў
    0.32
    года
    0.31
    рыва
    0.31
    Activations Density 0.401%

    No Known Activations