© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228286
    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_57_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
     pojem
    0.44
     Tanto
    0.42
     tanto
    0.40
     drug
    0.39
     atât
    0.39
     raft
    0.38
    ៖
    0.36
    tanto
    0.36
    ហារ
    0.36
    तिर
    0.36
    POSITIVE LOGITS
     Employment
    0.40
     doubly
    0.40
    <0x8E>
    0.39
    爹
    0.38
    rench
    0.38
    ской
    0.38
    braith
    0.38
    bra
    0.37
    妛
    0.37
    omol
    0.37
    Activations Density 0.000%

    No Known Activations