© 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. 9259
    Prev
    Next
    INDEX
    Explanations

    numbers between 1 and 10

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
    __(/*!
    -0.60
    oa̍t
    -0.54
    awtextra
    -0.54
    Naissance
    -0.54
    UnusedPrivate
    -0.52
     mergeFrom
    -0.52
     polaire
    -0.49
    retudo
    -0.48
     tranquille
    -0.46
    TagMode
    -0.45
    POSITIVE LOGITS
     Monate
    0.63
     Metern
    0.62
     []:
    0.59
     ioutil
    0.58
    TargetApi
    0.58
     Millionen
    0.56
     @"";
    0.55
     Tonnen
    0.54
    ParallelGroup
    0.53
    يكب
    0.53
    Activations Density 5.718%

    No Known Activations