© 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-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10348
    Prev
    Next
    INDEX
    Explanations

    the phrase "to the fullest extent"

    oai_token-act-pair · gemini-2.0-flash

    max

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -1.18
    __":
    
    -1.07
     שוליים
    -0.91
    findpost
    -0.89
     متعلقه
    -0.88
    __":
    -0.86
    migrationBuilder
    -0.85
    LookAnd
    -0.83
    UnusedPrivate
    -0.82
    __':
    
    -0.82
    POSITIVE LOGITS
    max
    0.47
     max
    0.46
    Max
    0.39
    jds
    0.39
    volles
    0.36
     maximale
    0.36
    マックス
    0.35
     aí
    0.35
     Max
    0.35
     verz
    0.35
    Activations Density 2.526%

    No Known Activations