INDEX

Explanations

Lithuanian words and proper nouns

oai_token-act-pair · gemini-2.0-flash

vos

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 SwitchCompat

-0.65

pertino

-0.62

twimg

-0.62

HomeAsUpEnabled

-0.61

ʺ

-0.58

kmale

-0.56

manjaro

-0.56

ValueGenerated

-0.55

ghar

-0.54

people

-0.54

POSITIVE LOGITS

<bos>

0.80

 hendes

0.51

 kasarigan

0.51

^(@)

0.51

NUMX

0.50

ंदीखरीदारी

0.50

 näm

0.50

posób

0.49

rollback

0.48

tolsó

0.48

Activations Density 0.160%

Lithuanian words and proper nouns

vos

No Comments

No Known Activations