© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198076
    Prev
    Next
    INDEX
    Explanations

    depends on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_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
    3
    0.46
    ę
    0.46
    imagen
    0.45
    足
    0.42
    ja
    0.42
    攝影
    0.41
     シューズ
    0.41
    ця
    0.41
    顧客
    0.40
     暗
    0.40
    POSITIVE LOGITS
    铉
    0.53
    uiscono
    0.48
    谄
    0.48
     carv
    0.46
    ল্যান্ডের
    0.46
    लैंड
    0.45
    DepartTime
    0.44
     tweaks
    0.43
    ນ
    0.43
     édition
    0.43
    Activations Density 0.000%

    No Known Activations