© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140426
    Prev
    Next
    INDEX
    Explanations

    low cost, childcare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
    u
    0.48
     NCAA
    0.47
    wiata
    0.46
     Ελλά
    0.42
     outlay
    0.42
     da
    0.42
    usstsein
    0.42
    മായിരുന്നു
    0.41
    άν
    0.41
     beginnetje
    0.40
    POSITIVE LOGITS
    Whether
    0.46
    Compatibility
    0.45
    LECTION
    0.44
     aktivit
    0.44
    5
    0.42
    Compatible
    0.42
    Performance
    0.41
    MOTION
    0.41
     t
    0.41
    唄
    0.41
    Activations Density 0.006%

    No Known Activations