INDEX

Explanations

characters or strings that appear to be code snippets

oai_token-act-pair · gemini-2.0-flash

computation

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

-0.60

 globalization

-0.50

 immemorial

-0.49

 urbanization

-0.43

 Bonita

-0.42

 scaven

-0.42

 maximized

-0.42

 Occident

-0.41

 parch

-0.41

 Inspir

-0.40

POSITIVE LOGITS

bootstrapcdn

0.79

 lèvres

0.72

 vermelhas

0.71

 AssemblyCulture

0.69

 réguli

0.68

+:+

0.68

AccessorTable

0.67

исленность

0.67

 ofthe

0.65

Lähteet

0.65

Activations Density 29.779%

characters or strings that appear to be code snippets

computation

No Comments

No Known Activations