© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10724
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives, especially "best".

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    NUMX
    -1.00
     Monfieur
    -0.98
    ^(@)
    -0.98
     Efq
    -0.96
     purpoſe
    -0.93
     كومونز
    -0.92
    ſelves
    -0.90
    saraba
    -0.89
     Jefus
    -0.89
    ſelf
    -0.89
    POSITIVE LOGITS
     most
    0.53
    con
    0.50
     Con
    0.48
     con
    0.47
    Con
    0.47
    bert
    0.43
    cen
    0.42
    _
    0.42
    CodeAttribute
    0.42
     besi
    0.41
    Activations Density 1.315%

    No Known Activations