INDEX

Explanations

terms related to mythical or divine power and judgement.

oai_token-act-pair · gemini-2.0-flash

how

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

import

-0.50

mergeFrom

-0.48

 roundabout

-0.47

炊

-0.46

zef

-0.45

hin

-0.45

娶

-0.45

uxxxx

-0.44

intar

-0.44

Geografía

-0.44

POSITIVE LOGITS



0.66

 unknownFields

0.63

 Wiktionnaire

0.59

ցված

0.57

 Walkover

0.57

__":

0.57

Rohy

0.56

CppMethod

0.56

<bos>

0.55

böz

0.53

Activations Density 0.953%

terms related to mythical or divine power and judgement.

how

No Comments

No Known Activations