INDEX

Explanations

words and phrases in languages other than English, mixed with some words related to communism and computing

oai_token-act-pair · gemini-2.0-flash

non-English text

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

and

-0.82

for

-0.73

but

-0.67

openzeppelin

-0.60

 wireType

-0.56

tvguidetime

-0.55

but

-0.53

Hochspringen

-0.52

 with

-0.51

Качество

-0.51

POSITIVE LOGITS

énario

0.57

IFER

0.54

 isolato

0.52

ainville

0.52

ünste

0.50

 שוליים

0.49

Rhestr

0.49

niß

0.48

luß

0.47

dymyr

0.47

Activations Density 0.669%

words and phrases in languages other than English, mixed with some words related to communism and computing

non-English text

No Comments

No Known Activations