© 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. 170753
    Prev
    Next
    INDEX
    Explanations

    error messages

    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
     er
    0.51
     ell
    0.39
     arresting
    0.38
    䣬
    0.38
    .-(
    0.37
     controlar
    0.36
     inciting
    0.36
    ភ
    0.35
     hủy
    0.35
     damaging
    0.35
    POSITIVE LOGITS
    Ca
    0.64
     Ca
    0.54
    ca
    0.43
    etc
    0.42
    Reduced
    0.42
    ……
    0.42
     ca
    0.41
    outputs
    0.41
    ….
    0.40
    Remote
    0.40
    Activations Density 0.001%

    No Known Activations