© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241312
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     funz
    0.38
    லய
    0.38
     makalah
    0.37
     sirop
    0.36
    endaft
    0.36
    颚
    0.36
     गठबंधन
    0.36
    UPDATE
    0.35
    addAlignment
    0.35
    गें
    0.35
    POSITIVE LOGITS
    borne
    0.39
     ver
    0.38
     لذلك
    0.38
    ค่อย
    0.38
     δεδο
    0.37
    ̣i
    0.37
    uncertain
    0.37
     买
    0.37
     dictum
    0.36
     미래
    0.36
    Activations Density 0.000%

    No Known Activations