INDEX

Explanations

references to the police and law enforcement.

oai_token-act-pair · gemini-2.0-flash

police

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 bezeichneter

-0.85

 محفوظة

-0.71

 Diſ

-0.61

CppCodeGen

-0.61

 שוליים

-0.61

 setInterval

-0.59

 Icarus

-0.57

 mxArray

-0.57

adaptiveStyles

-0.57

 Cassini

-0.57

POSITIVE LOGITS

car

0.48

صال

0.45

олові

0.44

بال

0.44

wydd

0.44

Car

0.43

hofer

0.43

 prés

0.43

 通販

0.43

car

0.42

Activations Density 1.248%

references to the police and law enforcement.

police

No Comments

No Known Activations