© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32398
    Prev
    Next
    INDEX
    Explanations

    Dostoevsky

    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
    Nat
    0.63
     Nat
    0.58
    nat
    0.53
     NAT
    0.53
    ナ
    0.53
     nat
    0.53
     النا
    0.52
     NAB
    0.52
    NAT
    0.50
     NAC
    0.50
    POSITIVE LOGITS
     Dost
    1.16
     dos
    1.05
     দো
    1.02
     Dos
    1.00
     dost
    0.98
     도
    0.95
    দো
    0.93
     Doo
    0.91
     Dois
    0.91
    Dos
    0.89
    Activations Density 0.021%

    No Known Activations