© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 69376
    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_51_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
    atus
    0.44
    Jw
    0.43
    টিস
    0.42
    ἦ
    0.41
     Int
    0.40
    ATUS
    0.39
    astically
    0.38
    targets
    0.38
    exploitation
    0.38
     ব্যান্ড
    0.38
    POSITIVE LOGITS
    urna
    0.42
     دست
    0.40
     somehow
    0.40
    देन
    0.39
     background
    0.38
     पुनर्
    0.38
    産
    0.38
    魂
    0.37
     blessed
    0.37
     reincarnation
    0.37
    Activations Density 0.000%

    No Known Activations