© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 167744
    Prev
    Next
    INDEX
    Explanations

    names starting C

    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_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
     critical
    0.42
     CR
    0.41
     cd
    0.40
     careful
    0.39
     आव्हान
    0.38
    쫄
    0.37
     ct
    0.37
    oreille
    0.37
     critica
    0.36
     КА
    0.36
    POSITIVE LOGITS
    C
    1.64
     Caleb
    1.12
     Cathy
    1.08
     Carly
    1.03
     Clyde
    0.96
     ค
    0.93
     Clover
    0.91
     Cramer
    0.90
     Cisco
    0.89
     Cary
    0.88
    Activations Density 0.027%

    No Known Activations