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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7039
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially semicolons and bracketed numbers on their own line

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    رشف
    -0.66
    oa̍t
    -0.61
    autique
    -0.60
     Unito
    -0.59
     alibi
    -0.59
     atheism
    -0.58
    Portale
    -0.58
     مشين
    -0.57
    OGND
    -0.57
     demografica
    -0.57
    POSITIVE LOGITS
    )$_
    0.75
    ]='\
    0.66
    ]+$
    0.60
    })->
    0.60
    ₂)
    0.59
    DrawerLayout
    0.58
    )$/,
    0.57
    "\"
    0.57
    matchCondition
    0.57
    ={`
    0.55
    Activations Density 5.285%

    No Known Activations