© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6966
    Prev
    Next
    INDEX
    Explanations

    a hodge-podge of common words such as prepositions, pronouns and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    moment

    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
     fly
    -0.47
    chts
    -0.47
     clear
    -0.46
     Piran
    -0.46
     chiaro
    -0.46
    CHA
    -0.46
     schli
    -0.46
    ,‎
    -0.45
    djangoproject
    -0.45
    Org
    -0.45
    POSITIVE LOGITS
     land
    0.84
    Land
    0.68
     विश्वसनीयता
    0.64
     Land
    0.62
    land
    0.61
     متعلقه
    0.60
    \{\\
    0.59
     OMITBAD
    0.59
    pushFollow
    0.59
    extAlignment
    0.57
    Activations Density 5.048%

    No Known Activations