© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149755
    Prev
    Next
    INDEX
    Explanations

    Q4_K_M quantization

    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_23_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
     chaqueta
    0.39
     stare
    0.39
    IRED
    0.39
     Interesse
    0.38
    再度
    0.38
    씩
    0.38
     분
    0.37
    نز
    0.37
     Deport
    0.37
     moor
    0.37
    POSITIVE LOGITS
    ဉ
    0.44
    ဥ
    0.42
    埙
    0.38
     práci
    0.38
    hasNext
    0.38
    重要的
    0.37
     erwäh
    0.37
    Ừ
    0.36
    orda
    0.36
     весьма
    0.36
    Activations Density 0.000%

    No Known Activations