INDEX

Explanations

code snippets, email addresses and dates in the format month day year

oai_token-act-pair · gemini-2.0-flash

Code and email addresses

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

########.

-0.55

 InputDecoration

-0.50

Hochspringen

-0.49

Хьажоргаш

-0.49

ḏ

-0.47

acquisto

-0.47

 fallu

-0.47

PageRoute

-0.47

 BoxDecoration

-0.46

الإنجليزية

-0.46

POSITIVE LOGITS

at

2.39

AT

2.34

AT

1.92

At

1.82

At

1.70

atnya

1.25

ats

1.19

atów

1.14

atı

1.09

ATR

1.07

Activations Density 17.395%

code snippets, email addresses and dates in the format month day year

Code and email addresses

No Comments

No Known Activations