© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5625
    Prev
    Next
    INDEX
    Explanations

    the number zero

    oai_token-act-pair · gemini-2.0-flash

    unspecified tokens or numbers

    np_token-act-pair-logits · gpt-4o-mini

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    SBATCH
    -0.74
    ulipas
    -0.73
     getItemCount
    -0.65
     SearchView
    -0.65
     مشين
    -0.64
    ]")]
    -0.63
     useAppContext
    -0.62
     خارجية
    -0.62
     doInBackground
    -0.62
    UnusedPrivate
    -0.61
    POSITIVE LOGITS
     tham
    0.46
     field
    0.43
    θλη
    0.41
    standes
    0.41
    ServiceModel
    0.41
     sensitivity
    0.41
    Vz
    0.41
     sacrificed
    0.40
    KO
    0.40
    fatti
    0.39
    Activations Density 0.450%

    No Known Activations