© 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. 4269
    Prev
    Next
    INDEX
    Explanations

    possession using apostrophe

    oai_token-act-pair · gemini-2.0-flash

    social media text 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
    europa
    -0.61
    CERN
    -0.60
    íncipe
    -0.59
    tiftung
    -0.57
    chanical
    -0.54
    Luxem
    -0.54
    OPC
    -0.53
    machus
    -0.52
    oceros
    -0.52
    xFFFFFFFF
    -0.52
    POSITIVE LOGITS
    👈
    0.42
     صوتيه
    0.37
    Cringe
    0.36
    Lol
    0.36
     sharing
    0.35
    Lmao
    0.34
     hâte
    0.33
    Hentet
    0.33
    Picking
    0.33
    turning
    0.32
    Activations Density 19.576%

    No Known Activations