INDEX

Explanations

various mathematical expressions, logical keywords like "the" "of" "for", content delivery terms, political terms, and words regarding a place of origin.

oai_token-act-pair · gemini-2.0-flash

say "C" words

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

 Thế

-0.39

RRect

-0.38

 Dostupné

-0.38

Бахар

-0.37

्वी

-0.37

DebuggerNonUser

-0.36

URLException

-0.36

 Độ

-0.35

 Rake

-0.35

shadowRadius

-0.35

POSITIVE LOGITS

Cur

1.04

Cl

1.02

Cas

1.00

Cam

1.00

Cou

0.99

Cos

0.97

Cor

0.96

Cr

0.96

Ch

0.96

Col

0.95

Activations Density 44.322%

various mathematical expressions, logical keywords like "the" "of" "for", content delivery terms, political terms, and words regarding a place of origin.

say "C" words

No Comments

No Known Activations

various mathematical expressions, logical keywords like "the" "of" "for", content delivery terms, political terms, and words regarding a place of origin.

say "C" words

No Comments

No Known Activations