© 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
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167539
    Prev
    Next
    INDEX
    Explanations

    equals or assign

    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_56_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
     cat
    0.85
    Cat
    0.82
     Cat
    0.76
    cat
    0.74
    猫
    0.69
    貓
    0.63
    CAT
    0.56
     cats
    0.55
    Kat
    0.55
     CAT
    0.52
    POSITIVE LOGITS
    ]=
    0.44
    ']=
    0.41
    }=\{
    0.41
    =:
    0.40
    }=-
    0.40
    =(
    0.39
    equal
    0.39
     }=
    0.38
    ={}
    0.38
    }=(\
    0.37
    Activations Density 0.005%

    No Known Activations