© 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
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167142
    Prev
    Next
    INDEX
    Explanations

    Musician

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Note
    0.43
     Tune
    0.42
    MAT
    0.41
     Tip
    0.40
    hom
    0.40
    cab
    0.39
    충
    0.39
    ADELPHIA
    0.39
    Contemporary
    0.37
     :-)
    0.37
    POSITIVE LOGITS
     caliper
    0.41
    ikker
    0.40
     instrumentation
    0.40
    സിൽ
    0.40
     strument
    0.39
    ँकि
    0.39
     paths
    0.38
     invari
    0.38
    icism
    0.38
    કના
    0.38
    Activations Density 0.000%

    No Known Activations