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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 63361
    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_41_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
    isers
    0.37
     °
    0.37
    পোষ
    0.36
     বৈঠকে
    0.36
    iners
    0.35
     ofici
    0.35
    orithms
    0.35
     Ramsay
    0.35
     А
    0.35
     buns
    0.35
    POSITIVE LOGITS
    तावनी
    0.40
    thione
    0.39
    October
    0.39
    crossed
    0.37
    Gosudarstvennyj
    0.37
    November
    0.37
    destroyed
    0.36
    vocabulary
    0.36
    गोर
    0.35
    hevik
    0.35
    Activations Density 0.000%

    No Known Activations