© 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. 846
    Prev
    Next
    INDEX
    Explanations

    parts of program code or other text containing computer-related keywords, particularly focusing on networking protocols and file system operations

    oai_token-act-pair · gemini-2.0-flash

    internet

    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
    ship
    -1.21
    s
    -1.19
    shop
    -1.09
    ski
    -1.08
    she
    -1.05
    sch
    -1.05
    sing
    -1.05
    sho
    -1.03
    school
    -1.01
    soft
    -1.01
    POSITIVE LOGITS
    nocache
    0.47
    \{\\
    0.41
    ئ
    0.39
    }".
    0.39
    }))
    0.38
    ρε
    0.38
    bindValue
    0.37
    andExpect
    0.37
    ]]
    0.37
    slidesToShow
    0.36
    Activations Density 32.991%

    No Known Activations