© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132654
    Prev
    Next
    INDEX
    Explanations

    landlords actions and conditions

    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_6_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
    <0xA8>
    0.93
     valiant
    0.89
     puddle
    0.88
     cellar
    0.85
     curator
    0.82
     marinade
    0.80
     river
    0.80
     messenger
    0.80
     seaport
    0.80
     parser
    0.79
    POSITIVE LOGITS
    0
    1.39
    p
    1.38
    this
    1.35
    name
    1.20
    d
    1.20
    that
    1.16
    ین
    1.14
    al
    1.12
    de
    1.12
    src
    1.11
    Activations Density 0.000%

    No Known Activations