© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205205
    Prev
    Next
    INDEX
    Explanations

    /

    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
    শিপ
    0.35
     அவரது
    0.35
    უქ
    0.35
    Ա
    0.35
    ফি
    0.35
    代表
    0.34
    successfully
    0.34
    الإ
    0.34
    涞
    0.33
     По
    0.33
    POSITIVE LOGITS
    -_
    0.44
     youre
    0.44
     Dont
    0.38
     dont
    0.38
    %-
    0.38
     -(
    0.38
    Dont
    0.38
    Were
    0.37
     couldnt
    0.37
     Were
    0.37
    Activations Density 0.000%

    No Known Activations