INDEX

Explanations

the word "stroke."

oai_token-act-pair · gemini-2.0-flash

stroke

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PreferredItem

-0.77

 GIPHY

-0.73

 Erle

-0.67

THISDAY

-0.66

 Nasional

-0.66

 Dase

-0.65

ptid

-0.62

himovic

-0.61

("")]

-0.61

iastes

-0.60

POSITIVE LOGITS

<bos>

0.75

+#+#

0.67

 referenties

0.56

elsif

0.54

Geplaatst

0.52

sizeCache

0.50

fjspx

0.49

IsContent

0.49

DispatchToProps

0.49

endfor

0.49

Activations Density 1.160%

the word "stroke."

stroke

No Comments

No Known Activations