© 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. 14911
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers

    oai_token-act-pair · gemini-2.0-flash

    code or legal contexts

    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
     africains
    -0.21
    <bos>
    -0.20
     actuels
    -0.18
     lemah
    -0.18
    …
    -0.17
    телите
    -0.15
     enggak
    -0.15
     roulant
    -0.14
     res
    -0.13
     σας
    -0.13
    POSITIVE LOGITS
    SourceChecksum
    1.22
    bootstrapcdn
    1.16
     AssemblyCompany
    1.13
    TagMode
    1.11
    OGND
    1.10
    ScopeManager
    1.08
    webElementXpaths
    1.05
    mybatisplus
    1.05
    enumii
    1.04
    +#+#
    1.04
    Activations Density 7.999%

    No Known Activations