© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10315
    Prev
    Next
    INDEX
    Explanations

    language related to providing information and advice

    oai_token-act-pair · gemini-2.0-flash

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     kasarigan
    -0.64
     vettoriale
    -0.57
    apunov
    -0.53
    Hauptartikel
    -0.52
     विश्वसनीयता
    -0.50
     fausse
    -0.50
    colta
    -0.50
     Ngb
    -0.49
    ंदीखरीदारी
    -0.48
     onFailure
    -0.47
    POSITIVE LOGITS
    Geplaatst
    0.67
    Personendaten
    0.58
     Cost
    0.57
    "])
    0.57
    ]));
    0.57
    raszam
    0.57
     cost
    0.56
    )");
    0.56
    rrggbb
    0.55
    raszamy
    0.54
    Activations Density 1.688%

    No Known Activations