© 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. 249249
    Prev
    Next
    INDEX
    Explanations

    Psalm

    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
     ch
    0.47
    فرض
    0.45
    Ch
    0.45
     چ
    0.44
    িং
    0.41
    لك
    0.39
    guj
    0.39
    lə
    0.38
    DSC
    0.38
    чений
    0.38
    POSITIVE LOGITS
    ੋਰ
    0.43
    med
    0.40
     principled
    0.38
     prayers
    0.38
     kas
    0.37
     adjusted
    0.37
     changed
    0.37
    禱
    0.36
    음을
    0.36
    ૧
    0.36
    Activations Density 0.000%

    No Known Activations