INDEX

Explanations

words related to a process changing over time

oai_token-act-pair · gemini-2.0-flash

actions or processes

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 calum

-0.55

ReturnValue

-0.54

SBATCH

-0.52

 المعيارى

-0.52

Demografia

-0.50

 olmak

-0.49

aarrggbb

-0.49

gapi

-0.49

NameInMap

-0.48

 toont

-0.48

POSITIVE LOGITS

ErrorListener

0.56

Референце

0.54

 AssemblyCulture

0.54

onien

0.51

 resourceCulture

0.50

UrlEncoded

0.49

hésite

0.49

matchCondition

0.48

 Chwiliwch

0.48

 transférez

0.46

Activations Density 7.012%

words related to a process changing over time

actions or processes

No Comments

No Known Activations