© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16320
    Prev
    Next
    INDEX
    Explanations

    quotation marks, especially at the beginning of lines, as well as the word "but" in certain contexts

    oai_token-act-pair · gemini-2.0-flash

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Monfieur
    -1.05
     Efq
    -0.97
     Theſe
    -0.94
     whoſe
    -0.94
     plufieurs
    -0.93
    CHREIB
    -0.92
    IBLIO
    -0.92
     Eſ
    -0.92
     avoient
    -0.91
     rempliss
    -0.91
    POSITIVE LOGITS
    I
    0.81
    ,
    0.70
     ...
    0.66
     …
    0.62
    A
    0.60
    The
    0.59
    :
    0.56
    In
    0.55
    We
    0.53
     ..
    0.51
    Activations Density 0.904%

    No Known Activations