© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11282
    Prev
    Next
    INDEX
    Explanations

    the string "ID", potentially when associated with URLs

    oai_token-act-pair · gemini-2.0-flash

    ID

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ID
    -2.34
     ID
    -2.08
     IDs
    -1.25
    IDs
    -1.13
    Id
    -1.02
    IDS
    -0.90
    id
    -0.85
    IDR
    -0.84
    IDI
    -0.81
     id
    -0.81
    POSITIVE LOGITS
     فريبيس
    0.84
    脚注の使い方
    0.77
     صوتيه
    0.76
     snippetHide
    0.72
     BoxFit
    0.70
    DebuggerNonUser
    0.69
     TestBed
    0.68
     tfsi
    0.67
    ruptedException
    0.65
    rrggbb
    0.65
    Activations Density 0.377%

    No Known Activations