INDEX

Explanations

words associated with businesses, organizations, and countries.

oai_token-act-pair · gemini-2.0-flash

Locations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

()?;

-0.54

 يتيمه

-0.53

 Jock

-0.52

 chân

-0.51

Mell

-0.50

arcoma

-0.49

 ✭✭

-0.48

principalTable

-0.47

 OFDb

-0.46

numbered

-0.45

POSITIVE LOGITS

 оригіналу

0.66

 demografica

0.59

.*")]

0.55

 '\\;'

0.54

 BoxDecoration

0.53

audiovisuel

0.53

 jadx

0.53

roveň

0.50

ContentAsync

0.49

 AttributeSet

0.49

Activations Density 4.489%

words associated with businesses, organizations, and countries.

Locations

No Comments

No Known Activations