© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207211
    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_56_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
    ்கள்
    0.39
     יכול
    0.38
    —
    0.38
    様
    0.38
    ுகள்
    0.37
    ,…
    0.37
    invite
    0.36
    ])+
    0.35
    賞
    0.35
    媳
    0.35
    POSITIVE LOGITS
     cheap
    0.85
    cheap
    0.79
     cheaper
    0.71
     Cheap
    0.71
     деше
    0.68
     inexpensive
    0.68
    Cheap
    0.67
     cheaply
    0.65
     सस्ता
    0.65
     cheapest
    0.63
    Activations Density 0.000%

    No Known Activations