© 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. 204804
    Prev
    Next
    INDEX
    Explanations

    US organizations

    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
    में
    0.44
    ’;
    0.44
    ’?
    0.42
    ?’”
    0.42
    ee
    0.38
    ”?
    0.38
     ¿?
    0.38
    కుని
    0.37
     ”.
    0.36
     '/':
    0.36
    POSITIVE LOGITS
    ｓ
    0.46
    sproz
    0.43
     ফোর্স
    0.42
    sn
    0.41
    spro
    0.41
     처
    0.41
    َس
    0.40
    sType
    0.40
    ס
    0.40
     forces
    0.40
    Activations Density 0.000%

    No Known Activations