© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154795
    Prev
    Next
    INDEX
    Explanations

    CP variations

    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_50_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
     hop
    0.40
     kav
    0.39
    桻
    0.38
     када
    0.38
     caring
    0.38
     proliferate
    0.38
    טת
    0.37
     hopping
    0.37
     hopped
    0.37
    ሉ
    0.36
    POSITIVE LOGITS
     CP
    3.55
    CP
    3.44
     cp
    3.36
    cp
    3.27
     Cp
    3.11
    Cp
    2.94
     सीपी
    2.58
     সিপি
    2.50
     CPD
    2.48
     CPS
    2.42
    Activations Density 0.000%

    No Known Activations