INDEX

Explanations

Code related

np_max-act-logits · gemini-2.0-flash

code snippets and HTML formatting tags

oai_token-act-pair · gemini-2.0-flash

HTML or XML code

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 numériques

-0.52

-0.48

니다

-0.44

mba

-0.43

-0.42

 sabes

-0.42

-0.41

-0.40

arb

-0.39

POSITIVE LOGITS

OGND

1.02

IsContent

0.95

WithIOException

0.82

 actionMode

0.81

ItemBackground

0.80

WriteTagHelper

0.76

Personendaten

0.75

AndEndTag

0.75

elemField

0.75

colgroup

0.75

Activations Density 0.284%

Code related

code snippets and HTML formatting tags

HTML or XML code

No Comments

No Known Activations