© 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. 8758
    Prev
    Next
    INDEX
    Explanations

    sentences where the speaker expresses a personal feeling or affect and references themselves directly.

    oai_token-act-pair · gemini-2.0-flash

    pronouns

    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
    ñora
    -0.80
    ")));
    -0.78
     <>",
    -0.76
    ]")]
    -0.75
    guenos
    -0.72
    ?")
    -0.71
     itſelf
    -0.70
     feroit
    -0.70
    yntaxException
    -0.69
     geox
    -0.69
    POSITIVE LOGITS
     complete
    0.56
     er
    0.50
     super
    0.50
     care
    0.45
     ut
    0.45
    jaro
    0.45
    倒
    0.45
     cal
    0.44
     regard
    0.43
     mais
    0.43
    Activations Density 1.587%

    No Known Activations