INDEX

Explanations

references to fictional battles.

oai_token-act-pair · gemini-2.0-flash

morality

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

ագրություններ

-0.52

ⓧ

-0.49

homonymie

-0.47

 مرئيه

-0.43

Einzelnachweise

-0.43

 <<<<<<<<<<<<<<

-0.42

onViewCreated

-0.40

listdir

-0.40

Interop

-0.40

MutableLiveData

-0.39

POSITIVE LOGITS

webElementXpaths

0.76

Rohy

0.63

byes

0.62

("]");

0.62

 klara

0.61

 bearer

0.57

 pesada

0.56

 réguli

0.55

цездатний

0.55

 épais

0.54

Activations Density 8.297%

references to fictional battles.

morality

No Comments

No Known Activations