© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217987
    Prev
    Next
    INDEX
    Explanations

    retina

    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_47_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
     voegen
    0.44
     Sandoval
    0.42
     छठी
    0.41
    鸞
    0.40
     broj
    0.39
     Corner
    0.38
    jit
    0.37
     பெயரை
    0.37
     Macs
    0.37
    lée
    0.37
    POSITIVE LOGITS
     ret
    1.38
    Ret
    1.20
     Ret
    1.18
    ret
    1.09
    RET
    0.91
     RET
    0.89
     retin
    0.80
     rét
    0.73
    退
    0.71
     retinol
    0.68
    Activations Density 0.002%

    No Known Activations