© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177196
    Prev
    Next
    INDEX
    Explanations

    H.P. Lovecraft

    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_50_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
     Petty
    0.47
     subv
    0.43
    чень
    0.42
    Chev
    0.39
     getN
    0.39
    耶
    0.38
     Gj
    0.38
     multig
    0.37
     گور
    0.37
    ധ്യ
    0.37
    POSITIVE LOGITS
    蹤
    0.47
     A
    0.46
    cule
    0.44
    A
    0.42
     Emil
    0.41
    Lambda
    0.39
    ronym
    0.38
    orno
    0.37
     الدم
    0.37
     Kamil
    0.37
    Activations Density 0.000%

    No Known Activations