INDEX

Explanations

research papers

np_max-act-logits · gemini-2.0-flash

words and symbols commonly used in mathematical or scientific writing, especially related to figures, graphs, and equations

oai_token-act-pair · gemini-2.0-flash

code or equation snippets

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

脚注の使い方

-0.86

 estekak

-0.74

Vidite

-0.67

__).

-0.65

rungsseite

-0.64

\{\\

-0.61

évaluateur

-0.60

findpost

-0.59

Portale

-0.59

 wigs

-0.57

POSITIVE LOGITS

InitVars

0.50

 chimiques

0.48

Initializable

0.48

ECA

0.46

hasMoreElements

0.46

 químicas

0.45

 kese

0.45

Ț

0.45

 modernas

0.44

というもの

0.44

Activations Density 15.272%

research papers

words and symbols commonly used in mathematical or scientific writing, especially related to figures, graphs, and equations

code or equation snippets

No Comments

No Known Activations