INDEX

Explanations

alphanumeric strings that look like they could be identifiers, often in a coding context

oai_token-act-pair · gemini-2.0-flash

Code IDs

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 unknownFields

-0.61

+:+

-0.56

 appelez

-0.55

Technologies

-0.53

 Crusoe

-0.52

']))

-0.52

odyear

-0.52

 technologies

-0.51

),

-0.50

Sirius

-0.50

POSITIVE LOGITS

awtextra

0.76

Autoritní

0.67

 entanto

0.63

脚注の使い方

0.62

 AttributeSet

0.62

 فريبيس

0.56

pyplot

0.52

mybatisplus

0.49

awakeFromNib

0.49

MethodImpl

0.48

Activations Density 1.056%

alphanumeric strings that look like they could be identifiers, often in a coding context

Code IDs

No Comments

No Known Activations