© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249855
    Prev
    Next
    INDEX
    Explanations

    comp

    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
     der
    0.68
    Der
    0.52
     Der
    0.50
     DER
    0.36
    der
    0.34
    ﾏ
    0.34
    ㎚
    0.34
    檄
    0.33
     Derby
    0.33
    繁
    0.33
    POSITIVE LOGITS
     comp
    3.83
     Comp
    3.38
    Comp
    3.30
    comp
    3.13
     ком
    2.36
     kom
    2.25
     comps
    2.22
     컴
    2.20
     komp
    2.11
     Kom
    2.08
    Activations Density 0.029%

    No Known Activations