© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3609
    Prev
    Next
    INDEX
    Explanations

    PC components and builds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    }$,
    0.77
    }-$
    0.72
     accounted
    0.71
    }$-
    0.71
     przeprowad
    0.71
    }$.
    0.70
    }$;
    0.68
    }=-\
    0.66
    }(-
    0.66
    })$,
    0.66
    POSITIVE LOGITS
     thrones
    0.68
    ט
    0.67
     throne
    0.65
    er
    0.64
     CPUs
    0.62
     mere
    0.61
     veil
    0.60
    le
    0.59
     tapestry
    0.59
    بيوتر
    0.58
    Activations Density 0.258%

    No Known Activations