INDEX

Explanations

code snippets including file paths and links

oai_token-act-pair · gemini-2.0-flash

scientific/artistic concepts

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

 eligible

-0.40

Eligible

-0.38

 arrend

-0.38

 desped

-0.38

 descuentos

-0.37

 ineligible

-0.36

Exceeded

-0.35

 attendance

-0.35

 aluguel

-0.35

 refugi

-0.35

POSITIVE LOGITS

 origami

0.66

 Sphinx

0.65

 helix

0.65

 Orpheus

0.63

ValueStyle

0.63

nemone

0.63

 Lilith

0.63

 Andromeda

0.62

 fractal

0.62

 torus

0.62

Activations Density 33.615%

code snippets including file paths and links

scientific/artistic concepts

No Comments

No Known Activations