© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39827
    Prev
    Next
    INDEX
    Explanations

    Dar

    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_57_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
    ermost
    0.43
    هما
    0.40
    ະ
    0.38
     vr
    0.38
     ISC
    0.38
    ept
    0.38
     vão
    0.38
     Casey
    0.37
     ISI
    0.37
     Isa
    0.37
    POSITIVE LOGITS
     es
    0.57
     э
    0.44
    jne
    0.40
    inn
    0.40
    use
    0.38
    melding
    0.38
    ssid
    0.37
    jalan
    0.37
    medal
    0.37
     el
    0.36
    Activations Density 0.000%

    No Known Activations