© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121334
    Prev
    Next
    INDEX
    Explanations

    numbers or ratings

    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_27_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
    ">(</
    0.40
     আবাস
    0.40
    㕩
    0.40
    salaryfrom
    0.40
     ፋ
    0.40
    ophenyl
    0.39
     एग्जांपल
    0.38
     silber
    0.38
     देन
    0.38
    ському
    0.38
    POSITIVE LOGITS
    0.40
    9
    0.39
    <0xC2>
    0.39
    begin
    0.38
     C
    0.37
     спо
    0.35
     Levy
    0.35
    loose
    0.35
     прави
    0.34
    4
    0.34
    Activations Density 0.001%

    No Known Activations