INDEX

Explanations

mentions of information, especially in an academic/technical context

oai_token-act-pair · gemini-2.0-flash

information

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 information

-2.64

information

-2.33

 Information

-2.31

Information

-2.28

 info

-2.22

 INFORMATION

-2.11

info

-2.00

 información

-1.94

INFORMATION

-1.90

 Info

-1.89

POSITIVE LOGITS

Erreferentziak

0.71

InjectAttribute

0.68

RegressionTest

0.65

 <<<<<<<<<<<<<<

0.65

httphttps

0.64

Vidite

0.63

featureID

0.63

GraphicsUnit

0.62

Personensuche

0.61

esterday

0.61

Activations Density 1.356%

mentions of information, especially in an academic/technical context

information

No Comments

No Known Activations