© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137180
    Prev
    Next
    INDEX
    Explanations

    matter how

    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
    O
    0.65
    ą
    0.63
    ী
    0.57
    asters
    0.55
    Larg
    0.55
    et
    0.53
    I
    0.53
    ू
    0.52
    াত
    0.50
    아
    0.50
    POSITIVE LOGITS
     ὁ
    0.65
     شہر
    0.64
     giochi
    0.63
     château
    0.63
     град
    0.61
     város
    0.61
     muere
    0.60
    မြို့
    0.60
    ció
    0.59
     город
    0.59
    Activations Density 0.001%

    No Known Activations