© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 274
    Prev
    Next
    INDEX
    Explanations

    the letters "rhs" and code syntax, potentially related to comparison operations within code.

    oai_token-act-pair · gemini-2.0-flash

    say "_"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Anfitrión
    -0.71
     EconPapers
    -0.71
     (“
    -0.71
     (
    -0.69
     “(
    -0.66
    存于互联网档案馆
    -0.63
    (“
    -0.63
     —
    -0.63
    contentLoaded
    -0.61
     --
    -0.60
    POSITIVE LOGITS
    _
    0.82
    _);
    0.55
    ]_
    0.53
    )_
    0.47
    }_
    0.47
    _));
    0.44
    )_/¯
    0.42
     !_
    0.41
    TagMode
    0.41
    OGND
    0.40
    Activations Density 5.482%

    No Known Activations