© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193964
    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_4_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
     a
    0.53
     Persian
    0.52
    CameraOpened
    0.52
     ELECTRO
    0.51
     RESPON
    0.51
     INSTIT
    0.48
     ASE
    0.48
     Lena
    0.46
     Chengdu
    0.46
     REFERENCE
    0.46
    POSITIVE LOGITS
    ed
    0.57
    -
    0.55
    ০০
    0.53
    e
    0.53
    er
    0.50
    ter
    0.48
    ០០
    0.48
    ००
    0.47
    HEY
    0.47
     terenie
    0.46
    Activations Density 0.000%

    No Known Activations