© 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
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 213140
    Prev
    Next
    INDEX
    Explanations

    Black Mesa and turn-based combat

    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_5_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
    い
    1.41
    ı
    1.27
    ை
    1.18
     of
    1.07
     OF
    1.06
     objected
    1.02
    سرائيل
    1.02
    ર
    1.01
    "%(
    1.00
     apparence
    0.98
    POSITIVE LOGITS
    for
    1.78
    ang
    1.60
    ur
    1.40
    is
    1.38
    water
    1.30
    which
    1.30
    to
    1.28
    this
    1.23
    ش
    1.22
    ’
    1.21
    Activations Density 0.022%

    No Known Activations