© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151774
    Prev
    Next
    INDEX
    Explanations

    from

    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_60_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
    e
    0.50
    V
    0.42
    data
    0.42
     e
    0.41
    lan
    0.41
    Vista
    0.41
     Dat
    0.40
    AS
    0.40
    list
    0.39
    An
    0.39
    POSITIVE LOGITS
     from
    0.52
     kutoka
    0.49
     dari
    0.49
    從
    0.48
    からの
    0.46
     నుండి
    0.46
     stung
    0.45
     từ
    0.45
     ascend
    0.45
     från
    0.43
    Activations Density 0.001%

    No Known Activations