© 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. 207060
    Prev
    Next
    INDEX
    Explanations

    holographic

    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
    eners
    0.41
     Fortunately
    0.37
     lézards
    0.36
    CCIÓN
    0.35
     prudent
    0.34
     dosage
    0.34
    獾
    0.34
     */;
    0.34
     reels
    0.34
     tabular
    0.34
    POSITIVE LOGITS
    Neha
    0.47
    Stephanie
    0.46
    राह
    0.44
     नेहा
    0.42
    ProjectType
    0.42
    sik
    0.41
    MatchType
    0.40
    Relationship
    0.39
    selfobj
    0.39
    런치
    0.38
    Activations Density 0.000%

    No Known Activations