© 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. 14484
    Prev
    Next
    INDEX
    Explanations

    the end of sentences, clauses, or quotes

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     that
    -1.16
     for
    -1.15
     to
    -1.14
     in
    -1.13
     there
    -1.12
     as
    -1.11
     they
    -1.10
     on
    -1.10
     this
    -1.10
     from
    -1.09
    POSITIVE LOGITS
    acetic
    0.53
    IBLES
    0.51
     ögon
    0.49
    "}")
    0.48
    ISES
    0.48
     dilatation
    0.47
     anledning
    0.47
    carbox
    0.46
     anastom
    0.46
     necrosis
    0.46
    Activations Density 5.599%

    No Known Activations