© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206788
    Prev
    Next
    INDEX
    Explanations

    Cannot read properties of

    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_19_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
    chim
    0.49
     already
    0.44
    ]/(
    0.43
    ftl
    0.42
    es
    0.40
    alis
    0.39
    得到
    0.39
     Architecture
    0.39
    gets
    0.38
     सेंट
    0.38
    POSITIVE LOGITS
     സൂ
    0.47
     thumbnail
    0.46
     menget
    0.45
    Ⲑ
    0.44
     గు
    0.44
     valence
    0.44
     DQ
    0.44
     Consultez
    0.44
    ༘
    0.43
     ব্যাবস্থা
    0.43
    Activations Density 0.001%

    No Known Activations