© 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. 9120
    Prev
    Next
    INDEX
    Explanations

    somewhat common, short words, particularly articles, prepositions, and pronouns seemingly without regard to their individual meaning or sentential context.

    oai_token-act-pair · gemini-2.0-flash

    Reviews of local places

    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
    #+#
    -0.71
    PointerException
    -0.59
    XmlAccessorType
    -0.58
    SizeMode
    -0.58
    WEBPACK
    -0.56
    SourceChecksum
    -0.56
    }*/
    -0.56
    brainly
    -0.54
     estekak
    -0.53
    úrese
    -0.52
    POSITIVE LOGITS
     purpose
    0.65
    Purpose
    0.52
     Purpose
    0.52
     الرياضيه
    0.49
    nande
    0.49
    purpose
    0.48
    tijden
    0.47
     Techn
    0.47
     Normdatei
    0.46
     Purposes
    0.45
    Activations Density 2.163%

    No Known Activations