© 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. 252994
    Prev
    Next
    INDEX
    Explanations

    Historically

    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
    Speaking
    0.56
    speaking
    0.54
    ,—
    0.54
     Speaking
    0.53
     ፣
    0.50
     speaking
    0.46
    had
    0.46
    以上の
    0.45
     patterns
    0.45
    .;
    0.44
    POSITIVE LOGITS
     common
    0.46
     compatible
    0.42
     significant
    0.40
     absent
    0.40
     conducive
    0.40
     described
    0.39
     Informed
    0.39
     incompatible
    0.39
     inscribed
    0.39
     informed
    0.38
    Activations Density 0.004%

    No Known Activations