© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21229
    Prev
    Next
    INDEX
    Explanations

    HAV

    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
    sys
    0.50
    ö
    0.48
     rel
    0.41
    quisition
    0.38
     integrated
    0.38
    agnet
    0.38
     para
    0.36
    dye
    0.36
    plug
    0.36
    ূন্য
    0.36
    POSITIVE LOGITS
    更大的
    0.39
    㤈
    0.38
    车载
    0.38
    auta
    0.37
     fortiter
    0.37
    र्ड
    0.37
     Poir
    0.36
     крово
    0.36
    ივ
    0.36
    ENTA
    0.36
    Activations Density 0.000%

    No Known Activations