© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2656
    Prev
    Next
    INDEX
    Explanations

    code snippets including array indexing and file handling

    oai_token-act-pair · gemini-2.0-flash

    say "end with ]"

    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
    bootstrapcdn
    -0.80
    principalColumn
    -0.77
    yntaxException
    -0.67
     IndexPath
    -0.66
     оригіналу
    -0.66
     anhyd
    -0.65
     дописавши
    -0.63
     invokingState
    -0.63
    queryInterface
    -0.62
    Personensuche
    -0.62
    POSITIVE LOGITS
    ]--;
    0.71
     are
    0.63
     is
    0.62
    )++;
    0.59
    ]='\
    0.57
     were
    0.49
    "]="
    0.45
    are
    0.45
    is
    0.45
    ]++;
    0.45
    Activations Density 4.279%

    No Known Activations