© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15115
    Prev
    Next
    INDEX
    Explanations

    take out or remove

    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_40_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
    ட்டு
    0.37
    [::-
    0.35
    deleteAll
    0.35
    రగ
    0.35
     tuan
    0.34
    终止
    0.34
     российских
    0.33
    ழுது
    0.33
    fea
    0.33
    ogène
    0.33
    POSITIVE LOGITS
     take
    1.63
    Take
    1.61
     Take
    1.60
    take
    1.55
     taken
    1.45
     TAKE
    1.43
    取
    1.40
     taking
    1.34
     Taking
    1.31
    taken
    1.31
    Activations Density 0.072%

    No Known Activations