INDEX

Explanations

text that is either French or Portuguese

oai_token-act-pair · gemini-2.0-flash

programming context

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

 سكانية

-0.73

rrggbb

-0.65

 himo

-0.64

 AppCompatTheme

-0.63

 EconPapers

-0.61

 لينك

-0.59

 мәкал

-0.59

 esternos

-0.58

 uVar

-0.57

 للاسماء

-0.57

POSITIVE LOGITS

 getById

0.67

ifoli

0.62

EMOS

0.62

liſh

0.58

ESSMENT

0.57

isielt

0.56

ząc

0.55

æus

0.55

.~(\

0.55

OLOGIES

0.55

Activations Density 0.349%

text that is either French or Portuguese

programming context

No Comments

No Known Activations