INDEX

Explanations

code snippets, especially related to data structures and programming languages

oai_token-act-pair · gemini-2.0-flash

code snippets

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

endpush

-0.68

BeginContext

-0.65

<?

-0.61

 kasarigan

-0.56

 "..\..\..\

-0.56

يكب

-0.55

GraphicsUnit

-0.55

tanleria

-0.54

 "..\..\

-0.54

nezeu

-0.52

POSITIVE LOGITS

طط

0.43

EARCH

0.43

RESH

0.42

DMF

0.42

MAP

0.41

odule

0.41

bmatrix

0.41

THON

0.41

DSA

0.40

SDF

0.40

Activations Density 21.038%

code snippets, especially related to data structures and programming languages

code snippets

No Comments

No Known Activations